datalab-to/indra
826 78PythonApache-2.0Updated 2 weeks ago
Fast CPU OCR that turns scans and PDFs into ordered markdown.
aicpudocument-parsingocronnxpdf
Our verdict: worth using
Provides a fast CPU‑only OCR that converts PDFs and images to markdown/text, useful for extracting document content for knowledge vaults and agent memory